» Download Article

Authors
Duc T. Nguyen; Mietek A. Brdys

Digital Object Identifier (DOI)
10.3182/20060830-2-SF-4903.00005

Page Numbers:
23-28

Index Terms
dynamic neural networks,robotic manipulators,on-line learning,non-linear control systems,feedback linearization,ultimate boundedness

Abstract
A dynamic neural network based algorithm for learning control of an unknown nonlinear continuous-time multiple-input-multiple-output plant with unmeasurable states is proposed in this paper. A new dynamic neural network structure is utilised to model the unknown plant dynamics through modelling the input-output mapping. A feedback linearization is applied to design controller for the neural model and the neural states are used as a source of precious information about current plant dynamics. A gradient based update of the weights is performed at discrete time instants over a moving measurement window in order to reduce the model output - real output mismatch. The learning controller is applied to a double link robot arm. Stability of the system is analysed through ultimate boundedness of all signals.

References

[1] Brdys, M. A., and Kulawski, G. J. (1999). "Dynamic
    neural controllers for induction motor." IEEE
    Transactions on Neural Networks, 10(2), 340-
    355.
[2] Brdys, M. A., Kulawski, G. J., and Quevedo, J.
    (1998). "Recurrent networks for nonlinear
    adaptive control." IEE Proceedings - Control
    Theory and Applications, 177-188.
[3] Brdys, M. A. and Nguyen, D. T "Dynamic neural
    network identification and control under
    unmeasurable plant states." Glasgow International
    Conference Control 2006.
[4] Horn, R. A. and Johnson, C. R. (1985). Matrix
    analysis, Cambrige university press.
[5] Harris, C. J., Lee, T. H., and Ge, S. S. (1998).
    Adaptive neural network control of robotic
    manipulators, World Scientific.
[6] Khalil, H. K. (2002). Nonlinear systems, Prince Hall.
[7] Poznyak, A. S., Wen Yu; Sanchez, E. N., and Perez,
    J. P. (1999). "Nonlinear adaptive trajectory
    tracking using dynamic neural networks." IEEE
    transactions on Neural networks, 10(6), 1402-
    1411.
[8] Poznyak, A. S., Sanchez, E. N., and Yu, W. (2001).
    Differential neural networks for robust nonlinear
    control - Identification, state estimation and
    trajectoty tracking, World Scientific.
[9] Ren, X. M., Rad, A. B., Chan, P. T., and Lo, W. L.
    (2003). "Identification and control of continuous-time
     nonlinear systems via dynamic neural
    networks." IEEE Transactions on Industrial
    Electronics, 50(3), 478-486.